Estimating PM2.5 utilizing multiple linear regression and ANN techniques

The accurate prediction of air pollutants, particularly Particulate Matter (PM), is critical to support effective and persuasive air quality management. Numerous variables influence the prediction of PM, and it's crucial to combine the most relevant input variables to ensure the most dependable...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2023-12, Vol.13 (1), p.22578-22578, Article 22578
Main Authors: Gulati, Sumita, Bansal, Anshul, Pal, Ashok, Mittal, Nitin, Sharma, Abhishek, Gared, Fikreselam
Format: Article
Language:English
Subjects:
639/166
704/172
Air pollution
Air quality
Algorithms
Bayesian analysis
Correlation coefficient
Humanities and Social Sciences
Mathematical models
multidisciplinary
Neural networks
Nitrogen dioxide
Outdoor air quality
Particulate matter
Predictions
Regression analysis
Science
Science (multidisciplinary)
Sulfur
Sulfur dioxide
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The accurate prediction of air pollutants, particularly Particulate Matter (PM), is critical to support effective and persuasive air quality management. Numerous variables influence the prediction of PM, and it's crucial to combine the most relevant input variables to ensure the most dependable predictions. This study aims to address this issue by utilizing correlation coefficients to select the most pertinent input and output variables for an air pollution model. In this work, PM 2.5 concentration is estimated by employing concentrations of sulfur dioxide, nitrogen dioxide, and PM 10 found in the air through the application of Artificial Neural Networks (ANNs). The proposed approach involves the comparison of three ANN models: one trained with the Levenberg–Marquardt algorithm (LM-ANN), another with the Bayesian Regularization algorithm (BR-ANN), and a third with the Scaled Conjugate Gradient algorithm (SCG-ANN). The findings revealed that the LM-ANN model outperforms the other two models and even surpasses the Multiple Linear Regression method. The LM-ANN model yields a higher R 2 value of 0.8164 and a lower RMSE value of 9.5223.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-023-49717-7